[m-rev.] for review: Add times operator for liblex

[Sebastian Godelet]

For review by anyone.

Branch: master.

---

Added the times operator for regular expressions,
such that one can express /[a-z]{10}/
in this way: letter * 10.

extras/lex/lex.m:
    Removed unused and unsafe str_foldr function,
    added (T * int) = regexp function.

extras/lex/samples/lex_demo.m:
    Removed whitespace in comments,
    added an input prompt,
    added a lexeme for '//' using the new '*' operator.
---
 extras/lex/lex.m              | 15 ++++++++-------
 extras/lex/samples/lex_demo.m | 11 +++++++----
 2 files changed, 15 insertions(+), 11 deletions(-)

diff --git a/extras/lex/lex.m b/extras/lex/lex.m
index 7570e32..2c47d91 100644
--- a/extras/lex/lex.m
+++ b/extras/lex/lex.m
@@ -117,6 +117,7 @@
 :- func ?(T) = regexp <= regexp(T).  % ?(R)       = R or null
 :- func +(T) = regexp <= regexp(T).  % +(R)       = R ++ *(R)
 :- func range(char, char) = regexp.  % range('a', 'z') =
any("ab...xyz") +:- func (T * int) = regexp <= regexp(T). % R * N = R
++ R ++ .. ++ R 
     % Some useful single-char regexps.
     %
@@ -837,19 +838,19 @@ anybut(S) = R :-
     ExcludedChars = sparse_bitset.list_to_set(string.to_char_list(S)),
     R = re(sparse_bitset.difference(valid_unicode_chars,
ExcludedChars)). 
-:- func str_foldr(func(char, T) = T, string, T, int) = T.
-
-str_foldr(Fn, S, X, I) =
-    ( if I < 0 then X
-               else str_foldr(Fn, S, Fn(string.det_index(S, I), X), I
- 1)
-    ).
-
 ?(R) = (R or null).
 
 +(R) = (R ++ *(R)).
 
 range(Start, End) = re(charset(char.to_int(Start), char.to_int(End))).
 
+R * N = Result :-
+    (   N < 0   -> unexpected($file, $pred, "N must be a non-negative
number")
+    ;   N = 0   -> Result = null
+    ;   N = 1   -> Result = re(R)
+    ;   Result = conc(re(R), (R * (N - 1)))
+    ).
+
 %-----------------------------------------------------------------------------%
 % Some useful single-char regexps.
 
diff --git a/extras/lex/samples/lex_demo.m
b/extras/lex/samples/lex_demo.m index 80a50d0..5cc9a26 100644
--- a/extras/lex/samples/lex_demo.m
+++ b/extras/lex/samples/lex_demo.m
@@ -6,7 +6,7 @@
 %
 % Copyright (C) 2001-2002 The University of Melbourne
 % Copyright (C) 2001 The Rationalizer Intelligent Software AG
-%   The changes made by Rationalizer are contributed under the terms 
+%   The changes made by Rationalizer are contributed under the terms
 %   of the GNU General Public License - see the file COPYING in the
 %   Mercury Distribution.
 %
@@ -46,8 +46,8 @@ I recognise the following words:
 ""and"", ""then"", ""the"", ""it"", ""them"", ""to"", ""on"".
 I also recognise Unicode characters:
 ""我"", ""会"", ""说"", ""中文""
-I also recognise Mercury-style comments, integers and floating point
-numbers, and a variety of punctuation symbols.
+I also recognise Mercury-style and C++-style comments, integers
+and floating point numbers, and a variety of punctuation symbols.
 
 Try me...
 
@@ -64,6 +64,7 @@ Try me...
     is det.
 
 tokenise_stdin(!LS) :-
+    lex.manipulate_source(io.print("> "), !LS),
     lex.read(Result, !LS),
     lex.manipulate_source(io.print(Result), !LS),
     lex.manipulate_source(io.nl, !LS),
@@ -107,6 +108,8 @@ lexemes = [
     ( "rat"             -> (func(Match) = noun(Match)) ),
     ( "mat"             -> (func(Match) = noun(Match)) ),
 
+    ( '/' * 2 ++ junk   -> (func(Match) = comment(Match)) ),
+
         % Here we use `or', rather than multiple lexemes.
         %
     ( "sat" or
@@ -117,7 +120,7 @@ lexemes = [
       "then"            -> (func(Match) = conj(Match)) ),
 
         % `\/' is a synonym for `or'.  Tell us which you prefer...
-        % 
+        %
     ( "the" \/
       "it" \/
       "them" \/
-- 
1.9.0